Back to Details

cli-anything-ollama

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

cli-anything-ollama

cli-anything-ollama

Local LLM inference and model management via the Ollama REST API. Designed for AI agents and power users who need to manage models, generate text, chat, and create embeddings without a GUI.
通过Ollama REST API实现本地LLM推理与模型管理。专为无需GUI即可管理模型、生成文本、聊天和创建嵌入的AI agents及高级用户设计。

Installation

安装

This CLI is installed as part of the cli-anything-ollama package:
bash
pip install cli-anything-ollama
Prerequisites:
  • Python 3.10+
  • Ollama must be installed and running (
    ollama serve
    )
该CLI作为cli-anything-ollama包的一部分进行安装：
bash
pip install cli-anything-ollama
前置要求：
  • Python 3.10+
  • 必须安装并运行Ollama（执行
    ollama serve
    ）

Usage

使用方法

Basic Commands

基础命令

bash
undefined
bash
undefined

Show help

显示帮助信息

cli-anything-ollama --help
cli-anything-ollama --help

Start interactive REPL mode

启动交互式REPL模式

cli-anything-ollama
cli-anything-ollama

List available models

列出可用模型

cli-anything-ollama model list
cli-anything-ollama model list

Run with JSON output (for agent consumption)

以JSON格式输出（供Agent调用）

cli-anything-ollama --json model list
undefined
cli-anything-ollama --json model list
undefined

REPL Mode

REPL模式

When invoked without a subcommand, the CLI enters an interactive REPL session:
bash
cli-anything-ollama
不指定子命令调用时，CLI会进入交互式REPL会话：
bash
cli-anything-ollama

Enter commands interactively with tab-completion and history

交互式输入命令，支持自动补全和历史记录

undefined
undefined

Command Groups

命令组

Model

Model（模型）

Model management commands.
CommandDescription
list
List locally available models
show
Show model details (parameters, template, license)
pull
Download a model from the Ollama library
rm
Delete a model from local storage
copy
Copy a model to a new name
ps
List models currently loaded in memory
模型管理命令。
命令描述
list
列出本地可用模型
show
显示模型详情（参数、模板、许可证）
pull
从Ollama库下载模型
rm
从本地存储删除模型
copy
将模型复制为新名称
ps
列出当前加载到内存中的模型

Generate

Generate（生成）

Text generation and chat commands.
CommandDescription
text
Generate text from a prompt
chat
Send a chat completion request
文本生成与聊天命令。
命令描述
text
根据提示词生成文本
chat
发送聊天补全请求

Embed

Embed（嵌入）

Embedding generation commands.
CommandDescription
text
Generate embeddings for text
嵌入生成命令。
命令描述
text
为文本生成嵌入向量

Server

Server（服务器）

Server status and info commands.
CommandDescription
status
Check if Ollama server is running
version
Show Ollama server version
服务器状态与信息命令。
命令描述
status
检查Ollama服务器是否运行
version
显示Ollama服务器版本

Session

Session（会话）

Session state commands.
CommandDescription
status
Show current session state
history
Show chat history for current session
会话状态命令。
命令描述
status
显示当前会话状态
history
显示当前会话的聊天历史

Examples

示例

List and Pull Models

列出并拉取模型

bash
undefined
bash
undefined

List available models

列出可用模型

cli-anything-ollama model list
cli-anything-ollama model list

Pull a model

拉取模型

cli-anything-ollama model pull llama3.2
cli-anything-ollama model pull llama3.2

Show model details

显示模型详情

cli-anything-ollama model show llama3.2
undefined
cli-anything-ollama model show llama3.2
undefined

Generate Text

生成文本

bash
undefined
bash
undefined

Stream text (default)

流式输出文本（默认模式）

cli-anything-ollama generate text --model llama3.2 --prompt "Explain quantum computing in one sentence"
cli-anything-ollama generate text --model llama3.2 --prompt "用一句话解释量子计算"

Non-streaming with JSON output (for agents)

非流式输出并返回JSON格式（供Agent调用）

cli-anything-ollama --json generate text --model llama3.2 --prompt "Hello" --no-stream
undefined
cli-anything-ollama --json generate text --model llama3.2 --prompt "Hello" --no-stream
undefined

Chat

聊天

bash
undefined
bash
undefined

Single-turn chat

单轮聊天

cli-anything-ollama generate chat --model llama3.2 --message "user:What is Python?"
cli-anything-ollama generate chat --model llama3.2 --message "user:什么是Python？"

Multi-turn chat

多轮聊天

cli-anything-ollama generate chat --model llama3.2
--message "user:What is Python?"
--message "user:How does it compare to JavaScript?"
cli-anything-ollama generate chat --model llama3.2
--message "user:什么是Python？"
--message "user:它和JavaScript相比有什么区别？"

Chat from JSON file

从JSON文件加载聊天内容

cli-anything-ollama generate chat --model llama3.2 --file messages.json
undefined
cli-anything-ollama generate chat --model llama3.2 --file messages.json
undefined

Embeddings

嵌入向量

bash
cli-anything-ollama embed text --model nomic-embed-text --input "Hello world"
cli-anything-ollama embed text --model nomic-embed-text --input "Hello" --input "World"
bash
cli-anything-ollama embed text --model nomic-embed-text --input "Hello world"
cli-anything-ollama embed text --model nomic-embed-text --input "Hello" --input "World"

Interactive REPL Session

交互式REPL会话

Start an interactive session for exploratory use.
bash
cli-anything-ollama
启动交互式会话用于探索性操作。
bash
cli-anything-ollama

Enter commands interactively

交互式输入命令

Use 'help' to see available commands

输入'help'查看可用命令

undefined
undefined

Connect to Remote Host

连接远程主机

bash
cli-anything-ollama --host http://192.168.1.100:11434 model list
bash
cli-anything-ollama --host http://192.168.1.100:11434 model list

State Management

状态管理

The CLI maintains lightweight session state:
  • Current host URL: Configurable via 
    --host
  • Chat history: Tracked for multi-turn conversations in REPL
  • Last used model: Shown in REPL prompt
该CLI维护轻量级会话状态：
  • 当前主机URL：可通过
    --host
    配置
  • 聊天历史：在REPL模式下跟踪多轮对话
  • 上次使用的模型：显示在REPL提示符中

Output Formats

输出格式

All commands support dual output modes:
  • Human-readable (default): Tables, colors, formatted text
  • Machine-readable (
    --json
    flag): Structured JSON for agent consumption
bash
undefined
所有命令支持两种输出模式：
  • 人类可读格式（默认）：表格、彩色显示、格式化文本
  • 机器可读格式（
    --json
    参数）：结构化JSON，供Agent调用
bash
undefined

Human output

人类可读输出

cli-anything-ollama model list
cli-anything-ollama model list

JSON output for agents

供Agent调用的JSON输出

cli-anything-ollama --json model list
undefined
cli-anything-ollama --json model list
undefined

For AI Agents

针对AI Agents的使用说明

When using this CLI programmatically:
  1. Always use 
    --json
    flag     for parseable output
  2. Check return codes - 0 for success, non-zero for errors
  3. Parse stderr for error messages on failure
  4. Use 
    --no-stream
     for generate/chat to get complete responses
  5. Verify Ollama is running with 
    server status
    before other commands
以编程方式使用该CLI时：
  1. 始终使用
    --json
    参数    以获得可解析的输出
  2. 检查返回码 - 0表示成功，非0表示错误
  3. 解析stderr获取失败时的错误信息
  4. 使用
    --no-stream
    参数    用于生成/聊天功能以获取完整响应
  5. 在执行其他命令前，通过
    server status
    验证Ollama是否运行

More Information

更多信息

  • Full documentation: See README.md in the package
  • Test coverage: See TEST.md in the package
  • Methodology: See HARNESS.md in the cli-anything-plugin
  • 完整文档：查看包中的README.md
  • 测试覆盖率：查看包中的TEST.md
  • 实现方法：查看cli-anything-plugin中的HARNESS.md

Version

版本

1.0.1
1.0.1